System

Abstract

An object of a system according to an embodiment is to automate management of a lost item and return of the lost item to an owner, and to quickly and efficiently perform the management and the return.SOLUTION: A system according to an embodiment includes a camera, a sensor, a generated AI, a database, a notifier, and a AI chat bot. The camera captures an image of the lost item. The sensor acquires position information of the lost item. The generation AI analyzes the date acquired from the camera and the sensor and extracts features of the lost item. The database registers the feature AI of the lost article analyzed by the generation means. The notification unit matches feature data of a lost item input by the owner through an online form or an application with data in the database, identifies a correct item, and notifies the owner of the item. The AI chat bot responds to an inquiry about a lost item.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, managing lost items and returning them to their owners was a time-consuming and labor-intensive process.

[0005] The system according to the embodiment aims to automate the management of lost items and their return to their owners quickly and efficiently. [Means for solving the problem]

[0006] The system according to the embodiment includes a camera, a sensor, a generation AI, a database, a notification unit, and an AI chatbot. The camera captures images of lost items. The sensor acquires location information of the lost items. The generation AI analyzes the data acquired from the camera and sensor and extracts the characteristics of the lost items. The database registers the characteristic data of the lost items analyzed by the generation AI. The notification unit matches the characteristic data of the lost items entered by the owner through an online form or app with the data in the database, identifies the correct item, and notifies the owner. The AI ​​chatbot responds to inquiries about the lost items. [Effects of the Invention]

[0007] The system according to the embodiment automates the management of lost items and their return to their owners, enabling this to be done quickly and efficiently. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A lost-and-found management system according to an embodiment of the present invention automates the lost-and-found management process at stations, aiming to quickly reunite lost items with their owners. In this system, a generation AI analyzes lost-item data collected by cameras and sensors and registers it in a database. When the owner enters the characteristics of the lost item through an online form or app, the generation AI performs image recognition and data matching to instantly identify the correct item and notify the owner. An AI chatbot also handles lost-item inquiries. This allows the lost-and-found management system to streamline the lost-item management process at stations and quickly reunite lost items with their owners. For example, it can significantly reduce the effort required for owners to search for lost items and shorten the time it takes for lost items to be found. Furthermore, responding to inquiries using the AI ​​chatbot reduces the burden on station staff and improves user satisfaction.

[0029] A lost-item management system according to an embodiment includes a camera, a sensor, a generation AI, a database, a notification unit, and an AI chatbot. The camera captures an image of the lost item. For example, a camera installed in a station captures an image of the lost item and sends the image data to the generation AI. The sensor acquires location information of the lost item. For example, the sensor acquires location information of the lost item and sends the data to the generation AI. The generation AI analyzes the data acquired from the camera and sensor to extract characteristics of the lost item. For example, the generation AI uses image analysis technology to extract characteristics such as color, shape, and size of the lost item. The generation AI also analyzes the location information to identify the exact location of the lost item. The database registers the characteristic data of the lost item analyzed by the generation AI. For example, the image, location information, and characteristic data of the lost item are stored in the database. The notification unit matches the characteristic data of the lost item entered by the owner through an online form or app with the data in the database, identifies the correct item, and notifies the owner. For example, if the owner enters "black wallet," the notification unit searches the database for "black wallet," identifies the most matching lost item, and notifies the owner. The AI ​​chatbot then responds to inquiries about lost items. For example, if the owner asks, "Where is my lost item?", the AI ​​chatbot responds, "It is being kept at the station's lost and found center." This allows the lost and found management system to streamline the lost and found management process at stations and quickly reunite owners with lost items. For example, it can significantly reduce the effort required for owners to search for lost items and shorten the time it takes for lost items to be found. Furthermore, responding to inquiries using the AI ​​chatbot reduces the burden on station staff and improves user satisfaction.

[0030] When the camera takes an image of the lost item, it also collects surrounding audio data, which the generating AI can analyze. For example, the camera collects surrounding audio data using microphones installed in the station. For example, it records the sound of the lost item being placed and surrounding conversations, and the generating AI analyzes that audio data to gain a detailed understanding of the situation of the lost item and the actions of the finder. This allows for a more detailed understanding of the situation of the lost item.

[0031] When collecting data on lost items, the generation AI can analyze the material or surface texture of the object. For example, the generation AI can analyze an image of the lost item taken with a camera and identify the material of the object (e.g., metal, plastic, cloth, etc.). This adds material information to the feature data of the lost item. The generation AI can also analyze the surface texture (e.g., smoothness, roughness, gloss, etc.) and add texture information to the feature data of the lost item. This allows for more detailed feature data to be extracted for the lost item.

[0032] The system can be linked to other security systems within the station and automatically issue alerts when lost items are found. For example, the system can be linked to the surveillance camera system within the station and automatically issue alerts when lost items are found. For example, when a surveillance camera detects a lost item, a notification is sent to station security staff. The system can also be linked to the access control system and restrict access to certain areas when lost items are found. This allows for a quick response when lost items are found.

[0033] The system utilizes drones to quickly locate lost items over a wide area. For example, the system uses drones to patrol train stations and surrounding areas to locate lost items. For example, a camera mounted on the drone takes a photo of the lost item, and the image is analyzed by the generating AI. The system also uses drones to efficiently monitor a wide area, allowing for the rapid discovery of lost items. This allows for the rapid discovery of lost items over a wide area.

[0034] The database can analyze the usage history or purchase history of lost items and add detailed information. For example, the database uses the serial number or manufacturing number of the lost item to allow the generation AI to analyze its usage history and purchase history. For example, it can identify the store where the lost item was purchased and how it was used. The database can also analyze how often and where the lost item was used and add detailed information. By adding detailed information about the lost item, it becomes more likely that it will be reunited with its owner.

[0035] The database can analyze the repair history or customization information of the lost item and highlight its individual features. For example, the database uses the serial number or manufacturing number of the lost item to allow the generation AI to analyze its repair history and customization information. For example, it identifies which repair shop the lost item was repaired at and how it was customized. The database can also analyze the details of the repairs and customization of the lost item and highlight its individual features. This highlights the individual features of the lost item, making it more likely to be reunited with its owner.

[0036] The database can generate a 3D model of the lost item to enable visual confirmation. In the database, for example, a generative AI generates the 3D model based on image data of the lost item. For example, a plurality of images are analyzed to create a three-dimensional model of the lost item. The database can also generate a 3D model of the lost item using 3D scanning technology to enable visual confirmation. By generating a 3D model of the lost item, it can be visually confirmed.

[0037] The database can automatically link related information about lost items. For example, the generation AI automatically links related information based on the serial number or manufacturing number of the lost item. For example, information about the manufacturer or the store where the item was purchased is registered in the database. The database can also automatically link related information about lost items, making it more likely that the item will be reunited with its owner. By automatically linking related information about lost items, it is more likely that the item will be reunited with its owner.

[0038] The generation AI provides an auto-completion function when the owner inputs the characteristics of the lost item, reducing the amount of work required for input. For example, when the owner starts to input "black wallet," the generation AI will suggest suggestions such as "black leather wallet" or "black long wallet." The generation AI can also predict the characteristics the owner will input based on past input data and suggest appropriate suggestions. This reduces the amount of work required for the owner to input information.

[0039] When the owner inputs the characteristics of the lost item, the generation AI can refer to past lost item data and suggest similar characteristics. For example, when the owner inputs the characteristics of the lost item, the generation AI can refer to past lost item data and suggest similar characteristics. For example, if the owner inputs "black wallet," the generation AI will make suggestions based on previously registered data such as "black leather wallet" and "black long wallet." The generation AI can also analyze past lost item data and suggest candidates that are closest to the characteristics input by the owner. This improves the accuracy of the owner's input.

[0040] The generation AI allows owners to input the characteristics of lost items by voice input or image upload, diversifying input methods. For example, the generation AI supports voice input when owners input the characteristics of lost items. For example, if the owner says "black wallet," the generation AI converts the voice into text and registers it as feature data. The generation AI also allows owners to upload images of lost items. For example, the owner can take a photo of the lost item, and the generation AI can analyze the image and register it as feature data. This diversifies input methods for owners.

[0041] The generation AI provides real-time feedback when the owner inputs the characteristics of the lost item, improving the accuracy of the input. For example, when the owner inputs the characteristics of the lost item, the generation AI provides real-time feedback. For example, if the owner inputs "black wallet," the generation AI will confirm, "Is it a black leather wallet?", improving the accuracy of the input. The generation AI can also analyze the characteristic data input by the owner and provide appropriate feedback. This improves the accuracy of the owner's input.

[0042] When performing image recognition, the generation AI also takes into account the aging of the lost item or signs of use, enabling more accurate matching. For example, when performing image recognition, the generation AI takes into account the aging of the lost item. For example, it analyzes the degree of discoloration and wear, and performs matching based on feature data that reflects the aging. The generation AI can also analyze signs of use on the lost item (for example, scratches, dirt, deformation, etc.) and reflect them in the feature data. This allows for more accurate matching by taking into account the aging of the lost item and signs of use.

[0043] When performing image recognition, the generation AI can analyze the background information of the lost item to improve matching accuracy. For example, when performing image recognition, the generation AI analyzes the location where the lost item was found. For example, matching accuracy can be improved based on data on lost items found in a specific area of ​​a station. The generation AI can also analyze the time of day the lost item was found and reflect this in the feature data. For example, matching accuracy can be improved based on information on the time of day the lost item was found. In this way, matching accuracy can be improved by analyzing the background information of the lost item.

[0044] When performing image recognition and data matching, the generative AI can analyze images taken from different viewpoints to improve matching accuracy. For example, when performing image recognition, the generative AI analyzes images taken from different viewpoints. For example, it can comprehensively analyze images of the front, back, and side of a lost item to improve matching accuracy. The generative AI can also extract the three-dimensional features of a lost item based on image data from different viewpoints. This improves matching accuracy by analyzing images taken from different viewpoints.

[0045] When performing image recognition and data matching, the generative AI can also analyze video data of lost items and take dynamic characteristics into account. For example, when performing image recognition, the generative AI analyzes video data of lost items. For example, it extracts the movement of the lost item and the surrounding situation from the video and performs matching while taking dynamic characteristics into account. The generative AI can also analyze the movement pattern and speed of the lost item based on the video data. This allows for matching that takes dynamic characteristics into account by analyzing the video data of lost items.

[0046] When notifying the owner, the notification unit can automatically generate a message that explains in detail where the lost item was found and the circumstances surrounding it. For example, when notifying the owner, the generation AI automatically generates a message that explains in detail where the lost item was found. For example, it sends a message such as, "The black wallet you are looking for was found near the south exit of the station." The notification unit can also generate a message that explains in detail the circumstances surrounding the discovery of the lost item. For example, it sends a message such as, "The lost item was found near the south exit of the station and is currently being kept at the lost and found center." In this way, when notifying the owner, a message that explains in detail where the lost item was found and the circumstances surrounding it is automatically generated, deepening the owner's understanding.

[0047] The notification unit can attach an image or video of the lost item when notifying the owner, allowing the owner to visually confirm the lost item. For example, when notifying the owner, the generation AI attaches an image of the lost item. For example, the image of the lost item is attached to a message such as "We have found the black wallet you are looking for" and sent. The notification unit can also attach a video of the lost item. For example, the video of the lost item is attached to a message such as "We have found the black wallet you are looking for" and sent. In this way, by attaching an image or video of the lost item when notifying the owner, the owner can visually confirm the lost item.

[0048] The notification unit can provide multiple notification methods when notifying the owner, ensuring that the notification is delivered reliably. For example, the generation AI can provide multiple notification methods when notifying the owner. For example, the owner can be allowed to select email, SMS, or app notification. The notification unit can also allow the owner to set their desired notification method in advance. This allows multiple notification methods to be provided, ensuring that the notification is delivered reliably.

[0049] When notifying the owner, the notification unit can provide a guide that explains in detail how to claim the lost item and the procedures for doing so. For example, when notifying the owner, the generation AI can provide a guide that explains in detail how to claim the lost item. For example, it can send a message such as, "The black wallet you are looking for can be claimed at the lost and found center at the station. Reception hours are 9:00-18:00." The notification unit can also provide a guide that explains in detail the procedures for claiming the lost item. For example, it can send a message such as, "When claiming a lost item, you will need identification." In this way, when notifying the owner, a guide that explains in detail how to claim the lost item and the procedures for doing so is provided, deepening the owner's understanding.

[0050] The AI ​​chatbot can refer to the owner's past inquiry history and provide a more personalized response.The AI ​​chatbot can refer to the owner's past inquiry history and provide a more personalized response.For example, if the owner was looking for a "black wallet" in the past, it could send a message such as "Did you find the black wallet you were looking for last time?".The AI ​​chatbot can also provide an appropriate response based on the owner's past inquiry content.By referring to the owner's past inquiry history, the AI ​​chatbot can provide a more personalized response.

[0051] The AI ​​chatbot can automatically provide relevant FAQs and guides in response to the owner's questions. For example, if the owner asks, "How do I claim my lost item?", it will send a message such as, "Click here to see how to claim your lost item." The AI ​​chatbot can also provide relevant guides in response to the owner's questions. For example, it will send a message such as, "Click here to see how to claim your lost item." In this way, the AI ​​chatbot can automatically provide relevant FAQs and guides in response to the owner's questions, quickly resolving the owner's concerns.

[0052] AI chatbots can support multiple languages, making them suitable for foreign users. AI chatbots can support multiple languages, making them suitable for foreign users. For example, they can support languages ​​such as English, Chinese, and Korean. AI chatbots can also respond to the needs of foreign users. By supporting multiple languages, they can also accommodate foreign users.

[0053] AI chatbots provide real-time translation functionality for their owners' questions, eliminating language barriers. For example, an AI chatbot can translate its owner's questions in real time and respond in the appropriate language. For example, if the owner asks a question in Japanese, the AI ​​chatbot will translate it into English and respond. AI chatbots can also translate their owners' questions into multiple languages ​​and respond in the appropriate language. This eliminates language barriers by providing real-time translation functionality for their owners' questions.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The system can support voice input when the owner inputs the characteristics of the lost item. For example, if the owner says "black wallet," the generation AI will convert that voice into text and register it as feature data. The system also allows the owner to upload images of the lost item. For example, the owner can take a photo of the lost item, and the generation AI can analyze the image and register it as feature data. This allows for a wider variety of input methods for the owner.

[0056] The system can be integrated with other security systems within the station to automatically issue alerts when lost items are found. For example, it can be integrated with the station's surveillance camera system to automatically issue alerts when lost items are found. When a surveillance camera detects a lost item, a notification is sent to station security staff. The system can also be integrated with the access control system to restrict access to certain areas when lost items are found. This allows for a quick response when lost items are found.

[0057] The system utilizes drones to quickly locate lost items over a wide area. For example, a drone patrols train stations and surrounding areas to locate lost items. A camera mounted on the drone takes a photo of the lost item, and the image is analyzed by the generating AI. The system also uses drones to efficiently monitor a wide area, allowing for the rapid discovery of lost items. This allows for the rapid discovery of lost items over a wide area.

[0058] When the owner inputs the characteristics of the lost item, the generation AI can refer to past lost item data and suggest similar characteristics. For example, when the owner inputs the characteristics of the lost item, the generation AI can refer to past lost item data and suggest similar characteristics. If the owner inputs "black wallet," the generation AI will make suggestions based on previously registered data such as "black leather wallet" and "black long wallet." The generation AI can also analyze past lost item data and suggest candidates that are closest to the characteristics input by the owner. This improves the accuracy of the owner's input.

[0059] The generative AI provides an auto-completion function when the owner inputs the characteristics of the lost item, reducing the amount of work required for input. For example, when the owner inputs the characteristics of the lost item, the generative AI provides an auto-completion function. If the owner starts to input "black wallet," the generative AI will suggest suggestions such as "black leather wallet" or "black long wallet." The generative AI can also predict the characteristics the owner will input based on past input data and suggest appropriate suggestions. This reduces the amount of work required for the owner to input information.

[0060] The generation AI provides real-time feedback when the owner inputs the characteristics of the lost item, improving the accuracy of the input. For example, when the owner inputs the characteristics of the lost item, real-time feedback is provided. If the owner inputs "black wallet," the generation AI will confirm, "Is it a black leather wallet?", improving the accuracy of the input. The generation AI can also analyze the characteristic data input by the owner and provide appropriate feedback. This improves the accuracy of the owner's input.

[0061] When performing image recognition, the generation AI can also take into account the aging of the lost item or signs of use, enabling more accurate matching. For example, when performing image recognition, the generation AI can take into account the aging of the lost item. It analyzes the degree of discoloration and wear, and performs matching based on feature data that reflects the aging. The generation AI can also analyze signs of use on the lost item (for example, scratches, dirt, deformation, etc.) and reflect them in the feature data. This allows for more accurate matching by taking into account the aging and signs of use of the lost item.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The camera takes an image of the lost item. For example, a camera installed in a station takes an image of the lost item and sends the image data to the generation AI. Step 2: The sensor acquires the location information of the lost item. For example, the sensor acquires the location information of the lost item and sends the data to the generation AI. Step 3: The generating AI analyzes the data obtained from the camera and sensors and extracts the characteristics of the lost item. For example, the generating AI uses image analysis technology to extract characteristics such as the color, shape, and size of the lost item. The generating AI also analyzes the location information and identifies the exact location of the lost item. Step 4: The database registers the characteristic data of the lost item analyzed by the generative AI. For example, the image, location information, and characteristic data of the lost item are stored in the database. Step 5: The notification unit matches the lost item characteristic data entered by the owner through the online form or app with the data in the database, identifies the correct item, and notifies the owner. For example, if the owner enters "black wallet," the notification unit will search the "black wallet" data in the database, identify the most matching lost item, and notify the owner. Step 6: The AI ​​chatbot responds to inquiries about the lost item. For example, if the owner asks, "Please tell me where my lost item is," the AI ​​chatbot will respond, "The lost item is being kept at the station's lost and found center."

[0064] (Example 2) A lost-and-found management system according to an embodiment of the present invention automates the lost-and-found management process at stations, aiming to quickly reunite lost items with their owners. In this system, a generation AI analyzes lost-item data collected by cameras and sensors and registers it in a database. When the owner enters the characteristics of the lost item through an online form or app, the generation AI performs image recognition and data matching to instantly identify the correct item and notify the owner. An AI chatbot also handles lost-item inquiries. This allows the lost-and-found management system to streamline the lost-item management process at stations and quickly reunite lost items with their owners. For example, it can significantly reduce the effort required for owners to search for lost items and shorten the time it takes for lost items to be found. Furthermore, responding to inquiries using the AI ​​chatbot reduces the burden on station staff and improves user satisfaction.

[0065] A lost-item management system according to an embodiment includes a camera, a sensor, a generation AI, a database, a notification unit, and an AI chatbot. The camera captures an image of the lost item. For example, a camera installed in a station captures an image of the lost item and sends the image data to the generation AI. The sensor acquires location information of the lost item. For example, the sensor acquires location information of the lost item and sends the data to the generation AI. The generation AI analyzes the data acquired from the camera and sensor to extract characteristics of the lost item. For example, the generation AI uses image analysis technology to extract characteristics such as color, shape, and size of the lost item. The generation AI also analyzes the location information to identify the exact location of the lost item. The database registers the characteristic data of the lost item analyzed by the generation AI. For example, the image, location information, and characteristic data of the lost item are stored in the database. The notification unit matches the characteristic data of the lost item entered by the owner through an online form or app with the data in the database, identifies the correct item, and notifies the owner. For example, if the owner enters "black wallet," the notification unit searches the database for "black wallet," identifies the most matching lost item, and notifies the owner. The AI ​​chatbot then responds to inquiries about lost items. For example, if the owner asks, "Where is my lost item?", the AI ​​chatbot responds, "It is being kept at the station's lost and found center." This allows the lost and found management system to streamline the lost and found management process at stations and quickly reunite owners with lost items. For example, it can significantly reduce the effort required for owners to search for lost items and shorten the time it takes for lost items to be found. Furthermore, responding to inquiries using the AI ​​chatbot reduces the burden on station staff and improves user satisfaction.

[0066] When the camera takes an image of the lost item, it also collects surrounding audio data, which the generating AI can analyze. For example, the camera collects surrounding audio data using microphones installed in the station. For example, it records the sound of the lost item being placed and surrounding conversations, and the generating AI analyzes that audio data to gain a detailed understanding of the situation of the lost item and the actions of the finder. This allows for a more detailed understanding of the situation of the lost item.

[0067] When collecting data on lost items, the generation AI can analyze the material or surface texture of the object. For example, the generation AI can analyze an image of the lost item taken with a camera and identify the material of the object (e.g., metal, plastic, cloth, etc.). This adds material information to the feature data of the lost item. The generation AI can also analyze the surface texture (e.g., smoothness, roughness, gloss, etc.) and add texture information to the feature data of the lost item. This allows for more detailed feature data to be extracted for the lost item.

[0068] The generation AI can analyze the emotions of the person who finds the lost item and estimate its importance. For example, the generation AI can capture the facial expressions of the person who finds the lost item with a camera and analyze the expressions. For example, it can detect expressions of surprise or joy and estimate the importance of the lost item. The generation AI can also analyze the voice data of the finder to estimate their emotions. For example, it can analyze the tone and speed of the voice and calculate an emotion score. This allows the importance of the lost item to be estimated and managed as a priority.

[0069] The system can be linked to other security systems within the station and automatically issue alerts when lost items are found. For example, the system can be linked to the surveillance camera system within the station and automatically issue alerts when lost items are found. For example, when a surveillance camera detects a lost item, a notification is sent to station security staff. The system can also be linked to the access control system and restrict access to certain areas when lost items are found. This allows for a quick response when lost items are found.

[0070] The system utilizes drones to quickly locate lost items over a wide area. For example, the system uses drones to patrol train stations and surrounding areas to locate lost items. For example, a camera mounted on the drone takes a photo of the lost item, and the image is analyzed by the generating AI. The system also uses drones to efficiently monitor a wide area, allowing for the rapid discovery of lost items. This allows for the rapid discovery of lost items over a wide area.

[0071] The generation AI can analyze the emotions of the person who finds the lost item and automatically generate a message of gratitude to the finder. For example, the generation AI can capture the facial expressions of the person who finds the lost item with a camera and analyze the expressions. For example, it can detect expressions of joy or surprise and automatically generate a message of gratitude to the finder. The generation AI can also analyze the finder's voice data and infer their emotions. For example, it can analyze the tone and speed of the voice and generate a message of gratitude. This allows the finder to express their gratitude.

[0072] The database can analyze the usage history or purchase history of lost items and add detailed information. For example, the database uses the serial number or manufacturing number of the lost item to allow the generation AI to analyze its usage history and purchase history. For example, it can identify the store where the lost item was purchased and how it was used. The database can also analyze how often and where the lost item was used and add detailed information. By adding detailed information about the lost item, it becomes more likely that it will be reunited with its owner.

[0073] The database can analyze the repair history or customization information of the lost item and highlight its individual features. For example, the database uses the serial number or manufacturing number of the lost item to allow the generation AI to analyze its repair history and customization information. For example, it identifies which repair shop the lost item was repaired at and how it was customized. The database can also analyze the details of the repairs and customization of the lost item and highlight its individual features. This highlights the individual features of the lost item, making it more likely to be reunited with its owner.

[0074] The database uses an emotion estimation function to analyze the emotions of the owner of a lost item and prioritizes the management of lost items with particularly high emotional value. For example, the database uses a generation AI to analyze the emotions of the owner of a lost item based on information provided by the owner. For example, the database identifies how much emotional value the owner has for the lost item and prioritizes its management. The database can also identify lost items with high emotional value based on the owner's emotion score and prioritize their management. This improves the satisfaction of the owner by prioritizing the management of lost items with high emotional value.

[0075] The database can generate a 3D model of the lost item to enable visual confirmation. In the database, for example, a generative AI generates the 3D model based on image data of the lost item. For example, a plurality of images are analyzed to create a three-dimensional model of the lost item. The database can also generate a 3D model of the lost item using 3D scanning technology to enable visual confirmation. By generating a 3D model of the lost item, it can be visually confirmed.

[0076] The database can automatically link related information about lost items. For example, the generation AI automatically links related information based on the serial number or manufacturing number of the lost item. For example, information about the manufacturer or the store where the item was purchased is registered in the database. The database can also automatically link related information about lost items, making it more likely that the item will be reunited with its owner. By automatically linking related information about lost items, it is more likely that the item will be reunited with its owner.

[0077] The database can use the emotion estimation function to analyze the emotion of the owner of the lost item and set a special notification for lost items with high emotional value. For example, the database uses the generation AI to analyze the emotion based on information provided by the owner of the lost item. For example, the database can identify how much emotional value the owner has for the lost item and set a special notification. The database can also set a special notification for lost items with high emotional value based on the owner's emotion score. In this way, setting a special notification for lost items with high emotional value improves the satisfaction of the owner.

[0078] The generation AI provides an auto-completion function when the owner inputs the characteristics of the lost item, reducing the amount of work required for input. For example, when the owner starts to input "black wallet," the generation AI will suggest suggestions such as "black leather wallet" or "black long wallet." The generation AI can also predict the characteristics the owner will input based on past input data and suggest appropriate suggestions. This reduces the amount of work required for the owner to input information.

[0079] When the owner inputs the characteristics of the lost item, the generation AI can refer to past lost item data and suggest similar characteristics. For example, when the owner inputs the characteristics of the lost item, the generation AI can refer to past lost item data and suggest similar characteristics. For example, if the owner inputs "black wallet," the generation AI will make suggestions based on previously registered data such as "black leather wallet" and "black long wallet." The generation AI can also analyze past lost item data and suggest candidates that are closest to the characteristics input by the owner. This improves the accuracy of the owner's input.

[0080] The emotion estimation function can analyze the owner's emotions when they input the characteristics of the lost item and provide an interface to reduce stress. For example, when the owner inputs the characteristics of the lost item, the emotion estimation function analyzes their facial expressions and estimates their emotions. For example, if the owner is feeling stressed, the generation AI can provide an interface that helps them relax. The emotion estimation function can also analyze the owner's voice data and estimate their emotions. For example, if the owner is feeling tense, the generation AI can play relaxing music. This reduces the owner's stress.

[0081] The generation AI allows owners to input the characteristics of lost items by voice input or image upload, diversifying input methods. For example, the generation AI supports voice input when owners input the characteristics of lost items. For example, if the owner says "black wallet," the generation AI converts the voice into text and registers it as feature data. The generation AI also allows owners to upload images of lost items. For example, the owner can take a photo of the lost item, and the generation AI can analyze the image and register it as feature data. This diversifies input methods for owners.

[0082] The generation AI provides real-time feedback when the owner inputs the characteristics of the lost item, improving the accuracy of the input. For example, when the owner inputs the characteristics of the lost item, the generation AI provides real-time feedback. For example, if the owner inputs "black wallet," the generation AI will confirm, "Is it a black leather wallet?", improving the accuracy of the input. The generation AI can also analyze the characteristic data input by the owner and provide appropriate feedback. This improves the accuracy of the owner's input.

[0083] The emotion estimation function can analyze the owner's emotions when they input the characteristics of the lost item and provide an interface that elicits positive emotions. For example, when the owner inputs the characteristics of the lost item, the emotion estimation function analyzes their facial expressions to estimate their emotions. For example, if the owner is feeling stressed, the generation AI can provide an interface that displays an encouraging message. The emotion estimation function can also analyze the owner's voice data to estimate their emotions. For example, if the owner is feeling anxious, the generation AI can display a message that gives them a sense of security. This elicits positive emotions from the owner.

[0084] When performing image recognition, the generation AI also takes into account the aging of the lost item or signs of use, enabling more accurate matching. For example, when performing image recognition, the generation AI takes into account the aging of the lost item. For example, it analyzes the degree of discoloration and wear, and performs matching based on feature data that reflects the aging. The generation AI can also analyze signs of use on the lost item (for example, scratches, dirt, deformation, etc.) and reflect them in the feature data. This allows for more accurate matching by taking into account the aging of the lost item and signs of use.

[0085] When performing image recognition, the generation AI can analyze the background information of the lost item to improve matching accuracy. For example, when performing image recognition, the generation AI analyzes the location where the lost item was found. For example, matching accuracy can be improved based on data on lost items found in a specific area of ​​a station. The generation AI can also analyze the time of day the lost item was found and reflect this in the feature data. For example, matching accuracy can be improved based on information on the time of day the lost item was found. In this way, matching accuracy can be improved by analyzing the background information of the lost item.

[0086] When performing image recognition, the generation AI can analyze the owner's emotions and prioritize matching lost items with high emotional value. For example, when the owner inputs the characteristics of the lost item, the generation AI analyzes their facial expressions to infer their emotions. For example, it will prioritize matching lost items that the owner has strong emotions about. The generation AI also analyzes the owner's voice data to infer their emotions. For example, if the owner is looking for a lost item with high emotional value, it can prioritize matching. This increases the owner's satisfaction by prioritizing matching lost items with high emotional value.

[0087] When performing image recognition and data matching, the generative AI can analyze images taken from different viewpoints to improve matching accuracy. For example, when performing image recognition, the generative AI analyzes images taken from different viewpoints. For example, it can comprehensively analyze images of the front, back, and side of a lost item to improve matching accuracy. The generative AI can also extract the three-dimensional features of a lost item based on image data from different viewpoints. This improves matching accuracy by analyzing images taken from different viewpoints.

[0088] When performing image recognition and data matching, the generative AI can also analyze video data of lost items and take dynamic characteristics into account. For example, when performing image recognition, the generative AI analyzes video data of lost items. For example, it extracts the movement of the lost item and the surrounding situation from the video and performs matching while taking dynamic characteristics into account. The generative AI can also analyze the movement pattern and speed of the lost item based on the video data. This allows for matching that takes dynamic characteristics into account by analyzing the video data of lost items.

[0089] When performing image recognition and data matching, the generative AI can analyze the owner's emotions and apply a special matching algorithm to lost items with high emotional value. For example, when the owner inputs the characteristics of the lost item, the generative AI analyzes their facial expressions to infer their emotions. For example, it applies a special matching algorithm to lost items for which the owner has strong emotions. The generative AI also analyzes the owner's voice data to infer their emotions. For example, if the owner is searching for a lost item with high emotional value, it can apply a special matching algorithm. This increases the owner's satisfaction by applying a special matching algorithm to lost items with high emotional value.

[0090] When notifying the owner, the notification unit can automatically generate a message that explains in detail where the lost item was found and the circumstances surrounding it. For example, when notifying the owner, the generation AI automatically generates a message that explains in detail where the lost item was found. For example, it sends a message such as, "The black wallet you are looking for was found near the south exit of the station." The notification unit can also generate a message that explains in detail the circumstances surrounding the discovery of the lost item. For example, it sends a message such as, "The lost item was found near the south exit of the station and is currently being kept at the lost and found center." In this way, when notifying the owner, a message that explains in detail where the lost item was found and the circumstances surrounding it is automatically generated, deepening the owner's understanding.

[0091] The notification unit can attach an image or video of the lost item when notifying the owner, allowing the owner to visually confirm the lost item. For example, when notifying the owner, the generation AI attaches an image of the lost item. For example, the image of the lost item is attached to a message such as "We have found the black wallet you are looking for" and sent. The notification unit can also attach a video of the lost item. For example, the video of the lost item is attached to a message such as "We have found the black wallet you are looking for" and sent. In this way, by attaching an image or video of the lost item when notifying the owner, the owner can visually confirm the lost item.

[0092] When notifying the owner, the notification unit can use the emotion estimation function to analyze the owner's emotions and generate an emotionally positive message. For example, when notifying the owner, the notification unit uses the generation AI to analyze the owner's emotions and generate a positive message. For example, if the owner is feeling stressed, the notification unit can send a message such as, "We have found the black wallet you were looking for. Don't worry." The notification unit can also generate an emotionally positive message based on the owner's emotion score. This increases the owner's sense of security by generating an emotionally positive message when notifying the owner.

[0093] The notification unit can provide multiple notification methods when notifying the owner, ensuring that the notification is delivered reliably. For example, the generation AI can provide multiple notification methods when notifying the owner. For example, the owner can be allowed to select email, SMS, or app notification. The notification unit can also allow the owner to set their desired notification method in advance. This allows multiple notification methods to be provided, ensuring that the notification is delivered reliably.

[0094] When notifying the owner, the notification unit can provide a guide that explains in detail how to claim the lost item and the procedures for doing so. For example, when notifying the owner, the generation AI can provide a guide that explains in detail how to claim the lost item. For example, it can send a message such as, "The black wallet you are looking for can be claimed at the lost and found center at the station. Reception hours are 9:00-18:00." The notification unit can also provide a guide that explains in detail the procedures for claiming the lost item. For example, it can send a message such as, "When claiming a lost item, you will need identification." In this way, when notifying the owner, a guide that explains in detail how to claim the lost item and the procedures for doing so is provided, deepening the owner's understanding.

[0095] When notifying the owner, the notification unit can use the emotion estimation function to analyze the owner's emotions and select an emotionally positive notification method. For example, when notifying the owner, the notification unit uses the generation AI to analyze the owner's emotions and select a positive notification method. For example, if the owner is feeling stressed, a gentle tone message is sent. The notification unit can also select an emotionally positive notification method based on the owner's emotion score. This increases the owner's sense of security by selecting an emotionally positive notification method when notifying the owner.

[0096] The AI ​​chatbot can refer to the owner's past inquiry history and provide a more personalized response.The AI ​​chatbot can refer to the owner's past inquiry history and provide a more personalized response.For example, if the owner was looking for a "black wallet" in the past, it could send a message such as "Did you find the black wallet you were looking for last time?".The AI ​​chatbot can also provide an appropriate response based on the owner's past inquiry content.By referring to the owner's past inquiry history, the AI ​​chatbot can provide a more personalized response.

[0097] The AI ​​chatbot can automatically provide relevant FAQs and guides in response to the owner's questions. For example, if the owner asks, "How do I claim my lost item?", it will send a message such as, "Click here to see how to claim your lost item." The AI ​​chatbot can also provide relevant guides in response to the owner's questions. For example, it will send a message such as, "Click here to see how to claim your lost item." In this way, the AI ​​chatbot can automatically provide relevant FAQs and guides in response to the owner's questions, quickly resolving the owner's concerns.

[0098] The AI ​​chatbot can use its emotion estimation function to analyze the owner's emotions and respond in an emotionally positive manner. For example, if the owner is feeling stressed, the AI ​​chatbot can respond in a gentle tone. The AI ​​chatbot can also respond appropriately based on the owner's emotion score. This allows the AI ​​chatbot to analyze the owner's emotions and respond in an emotionally positive manner, thereby improving the owner's satisfaction.

[0099] AI chatbots can support multiple languages, making them suitable for foreign users. AI chatbots can support multiple languages, making them suitable for foreign users. For example, they can support languages ​​such as English, Chinese, and Korean. AI chatbots can also respond to the needs of foreign users. By supporting multiple languages, they can also accommodate foreign users.

[0100] AI chatbots provide real-time translation functionality for their owners' questions, eliminating language barriers. For example, an AI chatbot can translate its owner's questions in real time and respond in the appropriate language. For example, if the owner asks a question in Japanese, the AI ​​chatbot will translate it into English and respond. AI chatbots can also translate their owners' questions into multiple languages ​​and respond in the appropriate language. This eliminates language barriers by providing real-time translation functionality for their owners' questions.

[0101] The AI ​​chatbot can use its emotion estimation function to analyze the owner's emotions and automatically generate a script for responding in an emotionally positive manner. For example, the AI ​​chatbot can analyze the owner's emotions and automatically generate a script for responding in a positive manner. For example, if the owner is feeling stressed, it can generate a script with a gentle tone. The AI ​​chatbot can also generate an appropriate script based on the owner's emotion score. This improves the owner's satisfaction by analyzing the owner's emotions and automatically generating a script for responding in an emotionally positive manner.

[0102] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0103] The system can support voice input when the owner inputs the characteristics of the lost item. For example, if the owner says "black wallet," the generation AI will convert that voice into text and register it as feature data. The system also allows the owner to upload images of the lost item. For example, the owner can take a photo of the lost item, and the generation AI can analyze the image and register it as feature data. This allows for a wider variety of input methods for the owner.

[0104] The system can be integrated with other security systems within the station to automatically issue alerts when lost items are found. For example, it can be integrated with the station's surveillance camera system to automatically issue alerts when lost items are found. When a surveillance camera detects a lost item, a notification is sent to station security staff. The system can also be integrated with the access control system to restrict access to certain areas when lost items are found. This allows for a quick response when lost items are found.

[0105] The generative AI can analyze the emotions of the person who finds the lost item and estimate its importance. For example, it can capture the facial expressions of the person who finds the lost item with a camera and analyze them. It can detect expressions of surprise or joy and estimate the importance of the lost item. The generative AI can also analyze the finder's voice data to estimate their emotions. It analyzes the tone and speed of the voice and calculates an emotion score. This allows it to estimate the importance of the lost item and manage it as a priority.

[0106] The system utilizes drones to quickly locate lost items over a wide area. For example, a drone patrols train stations and surrounding areas to locate lost items. A camera mounted on the drone takes a photo of the lost item, and the image is analyzed by the generating AI. The system also uses drones to efficiently monitor a wide area, allowing for the rapid discovery of lost items. This allows for the rapid discovery of lost items over a wide area.

[0107] When the owner inputs the characteristics of the lost item, the generation AI can refer to past lost item data and suggest similar characteristics. For example, when the owner inputs the characteristics of the lost item, the generation AI can refer to past lost item data and suggest similar characteristics. If the owner inputs "black wallet," the generation AI will make suggestions based on previously registered data such as "black leather wallet" and "black long wallet." The generation AI can also analyze past lost item data and suggest candidates that are closest to the characteristics input by the owner. This improves the accuracy of the owner's input.

[0108] The generative AI provides an auto-completion function when the owner inputs the characteristics of the lost item, reducing the amount of work required for input. For example, when the owner inputs the characteristics of the lost item, the generative AI provides an auto-completion function. If the owner starts to input "black wallet," the generative AI will suggest suggestions such as "black leather wallet" or "black long wallet." The generative AI can also predict the characteristics the owner will input based on past input data and suggest appropriate suggestions. This reduces the amount of work required for the owner to input information.

[0109] The emotion estimation function can analyze the owner's emotions when they input the characteristics of the lost item and provide an interface to reduce stress. For example, when the owner inputs the characteristics of the lost item, their facial expressions are analyzed to estimate their emotions. If the owner is feeling stressed, the generation AI will provide an interface that allows them to relax. The emotion estimation function can also analyze the owner's voice data to estimate their emotions. If the owner is feeling tense, the generation AI can play relaxing music, thereby reducing the owner's stress.

[0110] The generation AI provides real-time feedback when the owner inputs the characteristics of the lost item, improving the accuracy of the input. For example, when the owner inputs the characteristics of the lost item, real-time feedback is provided. If the owner inputs "black wallet," the generation AI will confirm, "Is it a black leather wallet?", improving the accuracy of the input. The generation AI can also analyze the characteristic data input by the owner and provide appropriate feedback. This improves the accuracy of the owner's input.

[0111] The emotion estimation function analyzes the owner's emotions when they input the characteristics of the lost item, and can provide an interface that elicits positive emotions. For example, when the owner inputs the characteristics of the lost item, their facial expressions are analyzed to estimate their emotions. If the owner is feeling stressed, the generation AI can provide an interface that displays an encouraging message. The emotion estimation function also analyzes the owner's voice data to estimate their emotions. If the owner is feeling anxious, the generation AI can display a message that provides reassurance. This elicits positive emotions from the owner.

[0112] When performing image recognition, the generation AI can also take into account the aging of the lost item or signs of use, enabling more accurate matching. For example, when performing image recognition, the generation AI can take into account the aging of the lost item. It analyzes the degree of discoloration and wear, and performs matching based on feature data that reflects the aging. The generation AI can also analyze signs of use on the lost item (for example, scratches, dirt, deformation, etc.) and reflect them in the feature data. This allows for more accurate matching by taking into account the aging and signs of use of the lost item.

[0113] The processing flow of the second embodiment will be briefly explained below.

[0114] Step 1: The camera takes an image of the lost item. For example, a camera installed in a station takes an image of the lost item and sends the image data to the generation AI. Step 2: The sensor acquires the location information of the lost item. For example, the sensor acquires the location information of the lost item and sends the data to the generation AI. Step 3: The generating AI analyzes the data obtained from the camera and sensors and extracts the characteristics of the lost item. For example, the generating AI uses image analysis technology to extract characteristics such as the color, shape, and size of the lost item. The generating AI also analyzes the location information and identifies the exact location of the lost item. Step 4: The database registers the characteristic data of the lost item analyzed by the generative AI. For example, the image, location information, and characteristic data of the lost item are stored in the database. Step 5: The notification unit matches the lost item characteristic data entered by the owner through the online form or app with the data in the database, identifies the correct item, and notifies the owner. For example, if the owner enters "black wallet," the notification unit will search the "black wallet" data in the database, identify the most matching lost item, and notify the owner. Step 6: The AI ​​chatbot responds to inquiries about the lost item. For example, if the owner asks, "Please tell me where my lost item is," the AI ​​chatbot will respond, "The lost item is being kept at the station's lost and found center."

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0125] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0128] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0143] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0155] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0156] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0157] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0158] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0159] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0160] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0161] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0163] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0164] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0174] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0175] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0176] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0180] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A camera and A sensor, Generative AI and A database, A notification unit; Equipped with AI chatbots, The camera is Take a picture of the lost item The sensor Obtain location information for lost items, The generated AI is Analyzing the data acquired from the camera and the sensor to extract characteristics of the lost item; The database comprises: Register the characteristic data of the lost item analyzed by the generating AI, The notification unit The system matches the characteristics of the lost item entered by the owner through an online form or app with the data in the database, identifies the correct item, and notifies the owner. The AI ​​chatbot: Responding to inquiries regarding lost property A system characterized by:

2. The system comprises: It works in conjunction with other security systems within the station, automatically issuing alerts when lost items are found.

2. The system of claim 1.

3. The database comprises: Analyze the usage history or purchase history of the lost item and add detailed information 2. The system of claim 1.

4. The generated AI is When the owner inputs the characteristics of the lost item, an auto-completion function is provided to reduce the effort of inputting.

2. The system of claim 1.

5. The AI ​​chatbot: Analyzes the owner's emotions using emotion estimation function and responds emotionally in a positive way 2. The system of claim 1.

Images